Main publication
- Hanhan Li, Ariel Gordon, Hang Zhao, Vincent Casser, Anelia Angelova: “Unsupervised Monocular Depth Learning in Dynamic Scenes.” Conference on Robot Learning (CoRL’20). (full text)
Related publications
- Hanhan Li, Ariel Gordon, Hang Zhao, V. Casser, Anelia Angelova: “Semantically-Agnostic Unsupervised Monocular Depth Learning in Dynamic Scenes.” Workshop on Perception for Autonomous Driving (ECCV’20).
- Vincent Casser, Soeren Pirk, Reza Mahjourian and Anelia Angelova: “Depth Prediction without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos.” Thirty-Third AAAI Conference on Artificial Intelligence (AAAI’19). (full text)
Abstract
We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily-underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including semantically-aware methods. The code is available here.